© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10418
    Prev
    Next
    INDEX
    Explanations

    series or franchise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Tits
    -0.21
    yt
    -0.20
    ä¸Ģéĺµ
    -0.20
    两åıª
    -0.19
    é£ķ
    -0.19
    Topology
    -0.18
    èµ³
    -0.18
    CRT
    -0.18
    æĥ¬æĦı
    -0.18
    çĤİçĥŃ
    -0.18
    POSITIVE LOGITS
    ç³»åĪĹ
    0.37
    ç³»åĪĹ产åĵģ
    0.28
    åIJĦç±»
    0.23
     series
    0.22
    ç³»åĪĹæ´»åĬ¨
    0.22
    ç¯ĩç«ł
    0.21
    åIJĦ个
    0.21
     SERIES
    0.21
    æĻ°
    0.21
    ãĤ·ãĥªãĥ¼ãĤº
    0.21
    Activations Density 0.847%

    No Known Activations